Papers › KPConvX: Modernizing Kernel Point Convolution with Kernel Attention
KPConvX: Modernizing Kernel Point Convolution with Kernel Attention
Hugues Thomas, Yao-Hung Hubert Tsai, Timothy D. Barfoot, Jian Zhang
In the field of deep point cloud understanding, KPConv is a unique architecture that uses kernel points to locate convolutional weights in space, instead of relying on Multi-Layer Perceptron (MLP) encodings. While it initially achieved success, it has since been surpassed by recent MLP networks that employ updated designs and training strategies. Building upon the kernel point principle, we present two novel designs: KPConvD (depthwise KPConv), a lighter design that enables the use of deeper architectures, and KPConvX, an innovative design that scales the depthwise convolutional weights of KPConvD with kernel attention values. Using KPConvX with a modern architecture and training strategy, we are able to outperform current state-of-the-art approaches on the ScanObjectNN, Scannetv2, and S3DIS datasets. We validate our design choices through ablation studies and release our code and models.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Point Cloud Classification | ScanObjectNN | KPConvX-L | Mean Accuracy | 88.1 | #27 of 77 | Archive leaderboard | report |
| 3D Point Cloud Classification | ScanObjectNN | KPConvX-L | Overall Accuracy | 89.3 | #27 of 77 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS Area5 | KPConvX-L | mAcc | 78.7 | #11 of 61 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS Area5 | KPConvX-L | mIoU | 73.5 | #11 of 61 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS Area5 | KPConvX-L | oAcc | 91.7 | #11 of 61 | Archive leaderboard | report |
| Semantic Segmentation | ScanNet | KPConvX-L | val mIoU | 76.3 | #13 of 45 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections